Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries full behavioral disclosure burden. It meaningfully discloses the daily refresh model, determinism, v1's structural-only component scope, the purpose of the not_evaluated list, and the weights parameter's one-call effect. This is strong context, though it stops short of covering auth, rate limits, or error conditions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Four dense paragraphs, each earning its place: return value, identifier format, v1 component scope, and optional reweighting. The core purpose is front-loaded in the first sentence, and there is no filler or repetition of schema content.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given there is no output schema, the description fully covers return elements (score, breakdown, 14-day trend, not_evaluated list), input format, and optional behavior. For a 2-parameter tool, this is effectively complete — the only minor gap is trend shape details, which is non-critical.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is only 50% (weights has a description; entity_id does not). The description compensates by fully specifying entity_id's `{entity_type}:{key}` format with concrete examples ('publisher:nytimes.com', 'ssp:pubmatic.com') and valid entity types. It also adds behavioral meaning to weights ('re-weights the stored components for this call') beyond the schema's bare type definition.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource: 'Returns the pre-computed 0.0–1.0 trust score for one entity, its component breakdown, and the 14-day trend.' It clearly distinguishes from siblings by scoping to a single entity and explicitly noting 'this endpoint never recomputes from raw data,' contrasting with batch or verification tools like sigil_score_batch.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives clear usage context — this is the fast, deterministic single-entity lookup ('scores are refreshed daily... never recomputes... fast and deterministic'). It implies when to use it (single entity, cached data) but does not explicitly name alternatives or exclusion cases, such as directing to sigil_score_batch for multiple entities or sigil_score_weights for weight management.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.